aboutsummaryrefslogtreecommitdiff
path: root/kernel/trace/trace_event_profile.c
blob: c1cc3ab633de6cab14b87463d4f70669feb8904b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
/*
 * trace event based perf counter profiling
 *
 * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
 *
 */

#include <linux/module.h>
#include <linux/kprobes.h>
#include "trace.h"


static char *perf_trace_buf;
static char *perf_trace_buf_nmi;

typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;

/* Count the events in use (per event id, not per instance) */
static int	total_profile_count;

static int ftrace_profile_enable_event(struct ftrace_event_call *event)
{
	char *buf;
	int ret = -ENOMEM;

	if (event->profile_count++ > 0)
		return 0;

	if (!total_profile_count) {
		buf = (char *)alloc_percpu(perf_trace_t);
		if (!buf)
			goto fail_buf;

		rcu_assign_pointer(perf_trace_buf, buf);

		buf = (char *)alloc_percpu(perf_trace_t);
		if (!buf)
			goto fail_buf_nmi;

		rcu_assign_pointer(perf_trace_buf_nmi, buf);
	}

	ret = event->profile_enable(event);
	if (!ret) {
		total_profile_count++;
		return 0;
	}

fail_buf_nmi:
	if (!total_profile_count) {
		free_percpu(perf_trace_buf_nmi);
		free_percpu(perf_trace_buf);
		perf_trace_buf_nmi = NULL;
		perf_trace_buf = NULL;
	}
fail_buf:
	event->profile_count--;

	return ret;
}

int ftrace_profile_enable(int event_id)
{
	struct ftrace_event_call *event;
	int ret = -EINVAL;

	mutex_lock(&event_mutex);
	list_for_each_entry(event, &ftrace_events, list) {
		if (event->id == event_id && event->profile_enable &&
		    try_module_get(event->mod)) {
			ret = ftrace_profile_enable_event(event);
			break;
		}
	}
	mutex_unlock(&event_mutex);

	return ret;
}

static void ftrace_profile_disable_event(struct ftrace_event_call *event)
{
	char *buf, *nmi_buf;

	if (--event->profile_count > 0)
		return;

	event->profile_disable(event);

	if (!--total_profile_count) {
		buf = perf_trace_buf;
		rcu_assign_pointer(perf_trace_buf, NULL);

		nmi_buf = perf_trace_buf_nmi;
		rcu_assign_pointer(perf_trace_buf_nmi, NULL);

		/*
		 * Ensure every events in profiling have finished before
		 * releasing the buffers
		 */
		synchronize_sched();

		free_percpu(buf);
		free_percpu(nmi_buf);
	}
}

void ftrace_profile_disable(int event_id)
{
	struct ftrace_event_call *event;

	mutex_lock(&event_mutex);
	list_for_each_entry(event, &ftrace_events, list) {
		if (event->id == event_id) {
			ftrace_profile_disable_event(event);
			module_put(event->mod);
			break;
		}
	}
	mutex_unlock(&event_mutex);
}

__kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
					int *rctxp, unsigned long *irq_flags)
{
	struct trace_entry *entry;
	char *trace_buf, *raw_data;
	int pc, cpu;

	pc = preempt_count();

	/* Protect the per cpu buffer, begin the rcu read side */
	local_irq_save(*irq_flags);

	*rctxp = perf_swevent_get_recursion_context();
	if (*rctxp < 0)
		goto err_recursion;

	cpu = smp_processor_id();

	if (in_nmi())
		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
	else
		trace_buf = rcu_dereference_sched(perf_trace_buf);

	if (!trace_buf)
		goto err;

	raw_data = per_cpu_ptr(trace_buf, cpu);

	/* zero the dead bytes from align to not leak stack to user */
	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;

	entry = (struct trace_entry *)raw_data;
	tracing_generic_entry_update(entry, *irq_flags, pc);
	entry->type = type;

	return raw_data;
err:
	perf_swevent_put_recursion_context(*rctxp);
err_recursion:
	local_irq_restore(*irq_flags);
	return NULL;
}
EXPORT_SYMBOL_GPL(ftrace_perf_buf_prepare);